summaryrefslogtreecommitdiffstats
path: root/Lib/lzma.py
blob: 011ad271fbb0869f3d4aefe7253267dff73ffd46 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
"""Interface to the liblzma compression library.

This module provides a class for reading and writing compressed files,
classes for incremental (de)compression, and convenience functions for
one-shot (de)compression.

These classes and functions support both the XZ and legacy LZMA
container formats, as well as raw compressed data streams.
"""

__all__ = [
    "CHECK_NONE", "CHECK_CRC32", "CHECK_CRC64", "CHECK_SHA256",
    "CHECK_ID_MAX", "CHECK_UNKNOWN",
    "FILTER_LZMA1", "FILTER_LZMA2", "FILTER_DELTA", "FILTER_X86", "FILTER_IA64",
    "FILTER_ARM", "FILTER_ARMTHUMB", "FILTER_POWERPC", "FILTER_SPARC",
    "FORMAT_AUTO", "FORMAT_XZ", "FORMAT_ALONE", "FORMAT_RAW",
    "MF_HC3", "MF_HC4", "MF_BT2", "MF_BT3", "MF_BT4",
    "MODE_FAST", "MODE_NORMAL", "PRESET_DEFAULT", "PRESET_EXTREME",

    "LZMACompressor", "LZMADecompressor", "LZMAFile", "LZMAError",
    "open", "compress", "decompress", "is_check_supported",
]

import builtins
import io
from _lzma import *
from _lzma import _encode_filter_properties, _decode_filter_properties


_MODE_CLOSED   = 0
_MODE_READ     = 1
_MODE_READ_EOF = 2
_MODE_WRITE    = 3

_BUFFER_SIZE = 8192


class LZMAFile(io.BufferedIOBase):

    """A file object providing transparent LZMA (de)compression.

    An LZMAFile can act as a wrapper for an existing file object, or
    refer directly to a named file on disk.

    Note that LZMAFile provides a *binary* file interface - data read
    is returned as bytes, and data to be written must be given as bytes.
    """

    def __init__(self, filename=None, mode="r", *,
                 format=None, check=-1, preset=None, filters=None):
        """Open an LZMA-compressed file in binary mode.

        filename can be either an actual file name (given as a str or
        bytes object), in which case the named file is opened, or it can
        be an existing file object to read from or write to.

        mode can be "r" for reading (default), "w" for (over)writing,
        "x" for creating exclusively, or "a" for appending. These can
        equivalently be given as "rb", "wb", "xb" and "ab" respectively.

        format specifies the container format to use for the file.
        If mode is "r", this defaults to FORMAT_AUTO. Otherwise, the
        default is FORMAT_XZ.

        check specifies the integrity check to use. This argument can
        only be used when opening a file for writing. For FORMAT_XZ,
        the default is CHECK_CRC64. FORMAT_ALONE and FORMAT_RAW do not
        support integrity checks - for these formats, check must be
        omitted, or be CHECK_NONE.

        When opening a file for reading, the *preset* argument is not
        meaningful, and should be omitted. The *filters* argument should
        also be omitted, except when format is FORMAT_RAW (in which case
        it is required).

        When opening a file for writing, the settings used by the
        compressor can be specified either as a preset compression
        level (with the *preset* argument), or in detail as a custom
        filter chain (with the *filters* argument). For FORMAT_XZ and
        FORMAT_ALONE, the default is to use the PRESET_DEFAULT preset
        level. For FORMAT_RAW, the caller must always specify a filter
        chain; the raw compressor does not support preset compression
        levels.

        preset (if provided) should be an integer in the range 0-9,
        optionally OR-ed with the constant PRESET_EXTREME.

        filters (if provided) should be a sequence of dicts. Each dict
        should have an entry for "id" indicating ID of the filter, plus
        additional entries for options to the filter.
        """
        self._fp = None
        self._closefp = False
        self._mode = _MODE_CLOSED
        self._pos = 0
        self._size = -1

        if mode in ("r", "rb"):
            if check != -1:
                raise ValueError("Cannot specify an integrity check "
                                 "when opening a file for reading")
            if preset is not None:
                raise ValueError("Cannot specify a preset compression "
                                 "level when opening a file for reading")
            if format is None:
                format = FORMAT_AUTO
            mode_code = _MODE_READ
            # Save the args to pass to the LZMADecompressor initializer.
            # If the file contains multiple compressed streams, each
            # stream will need a separate decompressor object.
            self._init_args = {"format":format, "filters":filters}
            self._decompressor = LZMADecompressor(**self._init_args)
            self._buffer = b""
            self._buffer_offset = 0
        elif mode in ("w", "wb", "a", "ab", "x", "xb"):
            if format is None:
                format = FORMAT_XZ
            mode_code = _MODE_WRITE
            self._compressor = LZMACompressor(format=format, check=check,
                                              preset=preset, filters=filters)
        else:
            raise ValueError("Invalid mode: {!r}".format(mode))

        if isinstance(filename, (str, bytes)):
            if "b" not in mode:
                mode += "b"
            self._fp = builtins.open(filename, mode)
            self._closefp = True
            self._mode = mode_code
        elif hasattr(filename, "read") or hasattr(filename, "write"):
            self._fp = filename
            self._mode = mode_code
        else:
            raise TypeError("filename must be a str or bytes object, or a file")

    def close(self):
        """Flush and close the file.

        May be called more than once without error. Once the file is
        closed, any other operation on it will raise a ValueError.
        """
        if self._mode == _MODE_CLOSED:
            return
        try:
            if self._mode in (_MODE_READ, _MODE_READ_EOF):
                self._decompressor = None
                self._buffer = b""
            elif self._mode == _MODE_WRITE:
                self._fp.write(self._compressor.flush())
                self._compressor = None
        finally:
            try:
                if self._closefp:
                    self._fp.close()
            finally:
                self._fp = None
                self._closefp = False
                self._mode = _MODE_CLOSED

    @property
    def closed(self):
        """True if this file is closed."""
        return self._mode == _MODE_CLOSED

    def fileno(self):
        """Return the file descriptor for the underlying file."""
        self._check_not_closed()
        return self._fp.fileno()

    def seekable(self):
        """Return whether the file supports seeking."""
        return self.readable() and self._fp.seekable()

    def readable(self):
        """Return whether the file was opened for reading."""
        self._check_not_closed()
        return self._mode in (_MODE_READ, _MODE_READ_EOF)

    def writable(self):
        """Return whether the file was opened for writing."""
        self._check_not_closed()
        return self._mode == _MODE_WRITE

    # Mode-checking helper functions.

    def _check_not_closed(self):
        if self.closed:
            raise ValueError("I/O operation on closed file")

    def _check_can_read(self):
        if self._mode not in (_MODE_READ, _MODE_READ_EOF):
            self._check_not_closed()
            raise io.UnsupportedOperation("File not open for reading")

    def _check_can_write(self):
        if self._mode != _MODE_WRITE:
            self._check_not_closed()
            raise io.UnsupportedOperation("File not open for writing")

    def _check_can_seek(self):
        if self._mode not in (_MODE_READ, _MODE_READ_EOF):
            self._check_not_closed()
            raise io.UnsupportedOperation("Seeking is only supported "
                                          "on files open for reading")
        if not self._fp.seekable():
            raise io.UnsupportedOperation("The underlying file object "
                                          "does not support seeking")

    # Fill the readahead buffer if it is empty. Returns False on EOF.
    def _fill_buffer(self):
        if self._mode == _MODE_READ_EOF:
            return False
        # Depending on the input data, our call to the decompressor may not
        # return any data. In this case, try again after reading another block.
        while self._buffer_offset == len(self._buffer):
            rawblock = (self._decompressor.unused_data or
                        self._fp.read(_BUFFER_SIZE))

            if not rawblock:
                if self._decompressor.eof:
                    self._mode = _MODE_READ_EOF
                    self._size = self._pos
                    return False
                else:
                    raise EOFError("Compressed file ended before the "
                                   "end-of-stream marker was reached")

            # Continue to next stream.
            if self._decompressor.eof:
                self._decompressor = LZMADecompressor(**self._init_args)

            self._buffer = self._decompressor.decompress(rawblock)
            self._buffer_offset = 0
        return True

    # Read data until EOF.
    # If return_data is false, consume the data without returning it.
    def _read_all(self, return_data=True):
        # The loop assumes that _buffer_offset is 0. Ensure that this is true.
        self._buffer = self._buffer[self._buffer_offset:]
        self._buffer_offset = 0

        blocks = []
        while self._fill_buffer():
            if return_data:
                blocks.append(self._buffer)
            self._pos += len(self._buffer)
            self._buffer = b""
        if return_data:
            return b"".join(blocks)

    # Read a block of up to n bytes.
    # If return_data is false, consume the data without returning it.
    def _read_block(self, n, return_data=True):
        # If we have enough data buffered, return immediately.
        end = self._buffer_offset + n
        if end <= len(self._buffer):
            data = self._buffer[self._buffer_offset : end]
            self._buffer_offset = end
            self._pos += len(data)
            return data if return_data else None

        # The loop assumes that _buffer_offset is 0. Ensure that this is true.
        self._buffer = self._buffer[self._buffer_offset:]
        self._buffer_offset = 0

        blocks = []
        while n > 0 and self._fill_buffer():
            if n < len(self._buffer):
                data = self._buffer[:n]
                self._buffer_offset = n
            else:
                data = self._buffer
                self._buffer = b""
            if return_data:
                blocks.append(data)
            self._pos += len(data)
            n -= len(data)
        if return_data:
            return b"".join(blocks)

    def peek(self, size=-1):
        """Return buffered data without advancing the file position.

        Always returns at least one byte of data, unless at EOF.
        The exact number of bytes returned is unspecified.
        """
        self._check_can_read()
        if not self._fill_buffer():
            return b""
        return self._buffer[self._buffer_offset:]

    def read(self, size=-1):
        """Read up to size uncompressed bytes from the file.

        If size is negative or omitted, read until EOF is reached.
        Returns b"" if the file is already at EOF.
        """
        self._check_can_read()
        if size == 0:
            return b""
        elif size < 0:
            return self._read_all()
        else:
            return self._read_block(size)

    def read1(self, size=-1):
        """Read up to size uncompressed bytes, while trying to avoid
        making multiple reads from the underlying stream.

        Returns b"" if the file is at EOF.
        """
        # Usually, read1() calls _fp.read() at most once. However, sometimes
        # this does not give enough data for the decompressor to make progress.
        # In this case we make multiple reads, to avoid returning b"".
        self._check_can_read()
        if (size == 0 or
            # Only call _fill_buffer() if the buffer is actually empty.
            # This gives a significant speedup if *size* is small.
            (self._buffer_offset == len(self._buffer) and not self._fill_buffer())):
            return b""
        if size > 0:
            data = self._buffer[self._buffer_offset :
                                self._buffer_offset + size]
            self._buffer_offset += len(data)
        else:
            data = self._buffer[self._buffer_offset:]
            self._buffer = b""
            self._buffer_offset = 0
        self._pos += len(data)
        return data

    def readline(self, size=-1):
        """Read a line of uncompressed bytes from the file.

        The terminating newline (if present) is retained. If size is
        non-negative, no more than size bytes will be read (in which
        case the line may be incomplete). Returns b'' if already at EOF.
        """
        self._check_can_read()
        # Shortcut for the common case - the whole line is in the buffer.
        if size < 0:
            end = self._buffer.find(b"\n", self._buffer_offset) + 1
            if end > 0:
                line = self._buffer[self._buffer_offset : end]
                self._buffer_offset = end
                self._pos += len(line)
                return line
        return io.BufferedIOBase.readline(self, size)

    def write(self, data):
        """Write a bytes object to the file.

        Returns the number of uncompressed bytes written, which is
        always len(data). Note that due to buffering, the file on disk
        may not reflect the data written until close() is called.
        """
        self._check_can_write()
        compressed = self._compressor.compress(data)
        self._fp.write(compressed)
        self._pos += len(data)
        return len(data)

    # Rewind the file to the beginning of the data stream.
    def _rewind(self):
        self._fp.seek(0, 0)
        self._mode = _MODE_READ
        self._pos = 0
        self._decompressor = LZMADecompressor(**self._init_args)
        self._buffer = b""
        self._buffer_offset = 0

    def seek(self, offset, whence=0):
        """Change the file position.

        The new position is specified by offset, relative to the
        position indicated by whence. Possible values for whence are:

            0: start of stream (default): offset must not be negative
            1: current stream position
            2: end of stream; offset must not be positive

        Returns the new file position.

        Note that seeking is emulated, sp depending on the parameters,
        this operation may be extremely slow.
        """
        self._check_can_seek()

        # Recalculate offset as an absolute file position.
        if whence == 0:
            pass
        elif whence == 1:
            offset = self._pos + offset
        elif whence == 2:
            # Seeking relative to EOF - we need to know the file's size.
            if self._size < 0:
                self._read_all(return_data=False)
            offset = self._size + offset
        else:
            raise ValueError("Invalid value for whence: {}".format(whence))

        # Make it so that offset is the number of bytes to skip forward.
        if offset < self._pos:
            self._rewind()
        else:
            offset -= self._pos

        # Read and discard data until we reach the desired position.
        self._read_block(offset, return_data=False)

        return self._pos

    def tell(self):
        """Return the current file position."""
        self._check_not_closed()
        return self._pos


def open(filename, mode="rb", *,
         format=None, check=-1, preset=None, filters=None,
         encoding=None, errors=None, newline=None):
    """Open an LZMA-compressed file in binary or text mode.

    filename can be either an actual file name (given as a str or bytes
    object), in which case the named file is opened, or it can be an
    existing file object to read from or write to.

    The mode argument can be "r", "rb" (default), "w", "wb", "x", "xb",
    "a", or "ab" for binary mode, or "rt", "wt", "xt", or "at" for text
    mode.

    The format, check, preset and filters arguments specify the
    compression settings, as for LZMACompressor, LZMADecompressor and
    LZMAFile.

    For binary mode, this function is equivalent to the LZMAFile
    constructor: LZMAFile(filename, mode, ...). In this case, the
    encoding, errors and newline arguments must not be provided.

    For text mode, a LZMAFile object is created, and wrapped in an
    io.TextIOWrapper instance with the specified encoding, error
    handling behavior, and line ending(s).

    """
    if "t" in mode:
        if "b" in mode:
            raise ValueError("Invalid mode: %r" % (mode,))
    else:
        if encoding is not None:
            raise ValueError("Argument 'encoding' not supported in binary mode")
        if errors is not None:
            raise ValueError("Argument 'errors' not supported in binary mode")
        if newline is not None:
            raise ValueError("Argument 'newline' not supported in binary mode")

    lz_mode = mode.replace("t", "")
    binary_file = LZMAFile(filename, lz_mode, format=format, check=check,
                           preset=preset, filters=filters)

    if "t" in mode:
        return io.TextIOWrapper(binary_file, encoding, errors, newline)
    else:
        return binary_file


def compress(data, format=FORMAT_XZ, check=-1, preset=None, filters=None):
    """Compress a block of data.

    Refer to LZMACompressor's docstring for a description of the
    optional arguments *format*, *check*, *preset* and *filters*.

    For incremental compression, use an LZMACompressor instead.
    """
    comp = LZMACompressor(format, check, preset, filters)
    return comp.compress(data) + comp.flush()


def decompress(data, format=FORMAT_AUTO, memlimit=None, filters=None):
    """Decompress a block of data.

    Refer to LZMADecompressor's docstring for a description of the
    optional arguments *format*, *check* and *filters*.

    For incremental decompression, use an LZMADecompressor instead.
    """
    results = []
    while True:
        decomp = LZMADecompressor(format, memlimit, filters)
        results.append(decomp.decompress(data))
        if not decomp.eof:
            raise LZMAError("Compressed data ended before the "
                            "end-of-stream marker was reached")
        if not decomp.unused_data:
            return b"".join(results)
        # There is unused data left over. Proceed to next stream.
        data = decomp.unused_data